TY - JOUR
T1 - Small Blob Detector Using Bi-Threshold Constrained Adaptive Scales
AU - Xu, Yanzhe
AU - Wu, Teresa
AU - Charlton, Jennifer R.
AU - Gao, Fei
AU - Bennett, Kevin M.
N1 - Funding Information:
Manuscript received October 4, 2020; accepted December 14, 2020. Date of publication December 21, 2020; date of current version August 20, 2021. This work was supported in part by the National Institute of Health Award under Grants R01DK110622, R01DK111861, in part by the Bruker ClinScan 7T MRI in the Molecular Imaging Core which was purchased with support from NIH Grant 1S10RR019911-01, and in part by the University of Virginia School of Medicine. (Corresponding author: Teresa Wu.) Yanzhe Xu and Fei Gao are with the School of Computing, Informatics and Decision Systems Engineering, and ASU-Mayo Center for Innovative Imaging, Arizona State University, USA.
Publisher Copyright:
© 1964-2012 IEEE.
PY - 2021/9
Y1 - 2021/9
N2 - Recent advances in medical imaging technology bring great promises for medicine practices. Imaging biomarkers are discovered to inform disease diagnosis, prognosis, and treatment assessment. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap among the blobs. This research proposes a Bi-Threshold Constrained Adaptive Scale (BTCAS) blob detector to uncover the relationship between the U-Net threshold and the Difference of Gaussian (DoG) scale to derive a multi-threshold, multi-scale small blob detector. With lower and upper bounds on the probability thresholds from U-Net, two binarized maps of the distance are rendered between blob centers. Each blob is transformed to a DoG space with an adaptively identified local optimum scale. A Hessian convexity map is rendered using the adaptive scale, and the under-segmentation typical of the U-Net is resolved. To validate the performance of the proposed BTCAS, a 3D simulated dataset (n = 20) of blobs, a 3D MRI dataset of human kidneys and a 3D MRI dataset of mouse kidneys, are studied. BTCAS is compared against four state-of-the-art methods: HDoG, U-Net with standard thresholding, U-Net with optimal thresholding, and UH-DoG using precision, recall, F-score, Dice and IoU. We conclude that BTCAS statistically outperforms the compared detectors.
AB - Recent advances in medical imaging technology bring great promises for medicine practices. Imaging biomarkers are discovered to inform disease diagnosis, prognosis, and treatment assessment. Detecting and segmenting objects from images are often the first steps in quantitative measurement of these biomarkers. The challenges of detecting objects in images, particularly small objects known as blobs, include low image resolution, image noise and overlap among the blobs. This research proposes a Bi-Threshold Constrained Adaptive Scale (BTCAS) blob detector to uncover the relationship between the U-Net threshold and the Difference of Gaussian (DoG) scale to derive a multi-threshold, multi-scale small blob detector. With lower and upper bounds on the probability thresholds from U-Net, two binarized maps of the distance are rendered between blob centers. Each blob is transformed to a DoG space with an adaptively identified local optimum scale. A Hessian convexity map is rendered using the adaptive scale, and the under-segmentation typical of the U-Net is resolved. To validate the performance of the proposed BTCAS, a 3D simulated dataset (n = 20) of blobs, a 3D MRI dataset of human kidneys and a 3D MRI dataset of mouse kidneys, are studied. BTCAS is compared against four state-of-the-art methods: HDoG, U-Net with standard thresholding, U-Net with optimal thresholding, and UH-DoG using precision, recall, F-score, Dice and IoU. We conclude that BTCAS statistically outperforms the compared detectors.
KW - Imaging biomarker
KW - adaptive Scales
KW - blob detection
KW - deep learning
KW - difference of gaussian (DoG)
KW - hessian analysis
UR - http://www.scopus.com/inward/record.url?scp=85098782349&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098782349&partnerID=8YFLogxK
U2 - 10.1109/TBME.2020.3046252
DO - 10.1109/TBME.2020.3046252
M3 - Article
C2 - 33347401
AN - SCOPUS:85098782349
VL - 68
SP - 2654
EP - 2665
JO - IRE transactions on medical electronics
JF - IRE transactions on medical electronics
SN - 0018-9294
IS - 9
M1 - 9301410
ER -